BR112023017266A2 - Coding Techniques for Neural Network Architectures - Google Patents

Coding Techniques for Neural Network Architectures

Info

Publication number
BR112023017266A2
BR112023017266A2 BR112023017266A BR112023017266A BR112023017266A2 BR 112023017266 A2 BR112023017266 A2 BR 112023017266A2 BR 112023017266 A BR112023017266 A BR 112023017266A BR 112023017266 A BR112023017266 A BR 112023017266A BR 112023017266 A2 BR112023017266 A2 BR 112023017266A2
Authority
BR
Brazil
Prior art keywords
data set
coding
neural network
network architectures
encode
Prior art date
Application number
BR112023017266A
Other languages
Portuguese (pt)
Inventor
June Namgoong
Naga Bhushan
Kumar Vitthaladevuni Pavan
Taesang Yoo
Original Assignee
Qualcomm Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112023017266A2 publication Critical patent/BR112023017266A2/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/06—Optimizing the usage of the radio link, e.g. header compression, information sizing, discarding information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T9/00—Image coding
    • G06T9/002—Image coding using neural networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
    • H04L69/04—Protocols for data compression, e.g. ROHC
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/08—Testing, supervising or monitoring using real traffic

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Security & Cryptography (AREA)
  • Multimedia (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

técnicas de codificação para arquiteturas de rede neural. métodos, sistemas, e dispositivos para comunicações sem fio são descritos. um equipamento de usuário (ue) pode receber uma indicação de uma ou mais operações de codificação a usar para codificar um conjunto de dados comprimidos, a uma ou mais operações de codificação incluindo uma operação de codificação diferencial, ou uma operação de codificação por entropia, ou ambas. em alguns exemplos, usando uma rede neural, o ue pode primeiro codificar um conjunto de dados com base em uma operação de codificação adicional para gerar um conjunto de dados comprimidos e então quantizar o conjunto de dados comprimidos codificados com base na operação de codificação adicional. subsequentemente, depois do conjunto de dados ter sido inicialmente codificado e então quantizado, o ue pode usar a indicação da uma ou mais operações de codificação para adicionalmente codificar e comprimir o conjunto de dados. o ue pode então transmitir o conjunto de dados para um segundo dispositivo com base na uma ou mais operações de codificaçãocoding techniques for neural network architectures. Methods, systems, and devices for wireless communications are described. a user equipment (ue) may receive an indication of one or more coding operations to use to encode a set of compressed data, one or more coding operations including a differential coding operation, or an entropy coding operation, or both. In some examples, using a neural network, the UE may first encode a data set based on an additional encoding operation to generate a compressed data set and then quantize the encoded compressed data set based on the additional encoding operation. Subsequently, after the data set has been initially encoded and then quantized, the UE may use the indication of one or more coding operations to further encode and compress the data set. The user can then transmit the data set to a second device based on one or more encoding operations

BR112023017266A 2021-03-05 2022-02-04 Coding Techniques for Neural Network Architectures BR112023017266A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/194,077 US20220284282A1 (en) 2021-03-05 2021-03-05 Encoding techniques for neural network architectures
PCT/US2022/015285 WO2022186947A1 (en) 2021-03-05 2022-02-04 Encoding techniques for neural network architectures

Publications (1)

Publication Number Publication Date
BR112023017266A2 true BR112023017266A2 (en) 2023-09-26

Family

ID=80445982

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112023017266A BR112023017266A2 (en) 2021-03-05 2022-02-04 Coding Techniques for Neural Network Architectures

Country Status (8)

Country Link
US (1) US20220284282A1 (en)
EP (1) EP4302232A1 (en)
JP (1) JP2024509502A (en)
KR (1) KR20230154014A (en)
CN (1) CN116917902A (en)
BR (1) BR112023017266A2 (en)
TW (1) TW202239152A (en)
WO (1) WO2022186947A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FI20206314A1 (en) * 2020-12-16 2022-06-17 Nokia Technologies Oy Estimating delay spread and doppler spread
CN116155453B (en) * 2023-04-23 2023-07-07 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) Decoding method and related equipment for dynamic signal-to-noise ratio

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018121670A1 (en) * 2016-12-30 2018-07-05 上海寒武纪信息科技有限公司 Devices for compression/decompression, system, chip, and electronic device

Also Published As

Publication number Publication date
EP4302232A1 (en) 2024-01-10
TW202239152A (en) 2022-10-01
KR20230154014A (en) 2023-11-07
WO2022186947A1 (en) 2022-09-09
US20220284282A1 (en) 2022-09-08
JP2024509502A (en) 2024-03-04
CN116917902A (en) 2023-10-20

Similar Documents

Publication Publication Date Title
BR112023017266A2 (en) Coding Techniques for Neural Network Architectures
MX2020005045A (en) Apparatus and method for encoding or decoding directional audio coding parameters using quantization and entropy coding.
CL2020001819A1 (en) Signaling mechanisms for equal ranges and other data parameters for video encoding
BR112015025478A2 (en) methods and apparatus for encoding and decoding data, encoded image data, data bearer, computer software, machine readable storage media, and storage and / or display apparatus, transmission, capture of video data
BR112021020796A2 (en) Video data processing method, apparatus for processing video data and non-transitory computer-readable media
MX2016011211A (en) Color-space inverse transform both for lossy and lossless encoded video.
AR110439A1 (en) VIDEO CODING METHOD, VIDEO DECODING METHOD, VIDEO CODING DEVICE AND VIDEO DECODING DEVICE
WO2019018120A8 (en) Communication techniques applying low-density parity-check code base graph selection
AU2019101588A4 (en) Methods and devices for encoding and decoding binary data
BR112019002429A2 (en) information transmission method, final transmission device, final receiving device, and computer readable media
BR112018073194A2 (en) Methods and Apparatus for the Efficient Generation of High Low Density (LDP) Parity Verification Codes
CL2021002762A1 (en) Block-Based Quantized Residual Domain Pulse Code Modulation Assignment for Intra Prediction Mode Derivation
Vestergaard et al. Generalized deduplication: Bounds, convergence, and asymptotic properties
BR112021018466A2 (en) Waste Processing in Video Coding
BR112021018470A2 (en) Residual Quantization in Video Coding
BR112013007612A2 (en) graphical data processing method and system for transmission to a remote computing device and computer readable storage medium
BR112023002815A2 (en) CONFIGURABLE INDICATORS FOR COMPRESSION AND CHANNEL STATE FEEDBACK
PE20231246A1 (en) VIDEO ENCODER, VIDEO DECODER, METHODS FOR ENCODING AND DECODING AND VIDEO DATA STREAM TO REALIZE ADVANCED VIDEO CODING CONCEPTS
EP4280604A3 (en) Guaranteed data compression
RU2012103446A (en) METHOD AND DEVICE FOR CODING AND DECODING OF AUDIO SIGNALS (OPTIONS)
EP4122137A4 (en) Methods and systems for network coding using cross-packet check blocks
BR112022013594A2 (en) VIDEO PROCESSING METHOD AND APPARATUS, METHOD FOR STORING A STREAM OF BITS, AND, COMPUTER READable MEDIA
CL2021001707A1 (en) An encoder, decoder, and corresponding methods using compact mv storage
MX2023004081A (en) Coding of component of color attributes in geometry-based point cloud compression (g-pcc).
BR112023002289A2 (en) ENCODING A DATA SET USING A NEURAL NETWORK FOR UPLINK COMMUNICATION